whereismyai
Claude Code Local
Claude Code Local is a Python server running open AI models on Mac chips to power Claude Code offline.
Claude Code Local is a small Python server that runs open AI models locally on Apple Silicon Macs using Apple MLX. It answers Claude Code requests in Anthropic API format so the coding assistant works completely offline with no cloud model or API key required. The tool includes a native MLX server with streaming support, tool-call format conversion, tool JSON repair, and prompt cache reuse for long sessions. Setup scripts check available Mac memory and automatically select and download a compatible model like Gemma or Qwen. Users can run Claude Code, use a lightweight terminal coding agent, or extend usage with browser, voice, and phone modes.
Claude Code Local at a glance
Key features
- Speaks Anthropic Messages API with streaming
- Converts model tool calls to Claude Code format
- Repairs garbled tool JSON automatically
- Reuses prompt cache between turns
- Automatic setup script for model selection and installation
- Terminal coding agent with fixed system prompt
- Conversation resume support for when Claude credits run out
Use it for
- Run Claude Code locally without internet or API keys
- Continue coding sessions after hitting Claude usage limits
- Execute local AI models on Apple Silicon hardware
- Drive browser automation with local models
Companions
Tools that articles about Claude Code Local recommend using with it, each with its job.
- Claude Code — Built to work with Claude Code.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Playwright MCP — Enables LLMs to interact with web pages using structured accessibility snapshots.
- GitHub MCP Server — Reads pull requests, issues and code search on GitHub.
- Superpowers — Brainstorm, plan and execute skills for bigger tasks.
- gstack — Skill bundle for planning, review and shipping.
Alternatives to Claude Code Local
- claudecode.nvim — Adds native AI coding assistant functionality to Neovim.
- Claude Code Router — It centralizes control of AI agent requests with intelligent routing and observability.
- opcode — Turns terminal Claude Code workflows into an intuitive visual interface.
- CLI Dispatch — Runs alternative AI models as workers from inside Claude Code.
- carcode — Control Claude Code, GitHub, and Slack entirely by voice over Apple CarPlay.
- Juiced — Runs Claude Code in a persistent cloud workspace while the laptop is closed.
- Claude Code Mode — Reduces context token usage by returning only the final program result.
- Claude Code Workflows — Provides pre-built, automated workflows for Claude Code development processes.
- Claude Code Session Tracker — Monitor Claude Code usage limits and token history in a single local interface.
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
- Local Code Community — Runs local offline models and built-in tools securely inside an app sandbox.
- Claude Code Proxy — Runs Anthropic-compatible clients with Gemini or OpenAI models.
All Claude Code Local alternatives